Reconstructing echoes completely submerged in background noise by a stacked denoising autoencoder method for low-power EMAT testing

电磁声换能器 声学 降噪 信号(编程语言) 计算机科学 噪音(视频) 功率(物理) 自编码 人工神经网络 材料科学 人工智能 超声波检测 超声波传感器 物理 量子力学 图像(数学) 程序设计语言
作者
Jinjie Zhou,Dianrui Yu,Xiang Li,Yang Zheng,Yao Liu
出处
期刊:Measurement Science and Technology [IOP Publishing]
卷期号:34 (12): 125910-125910
标识
DOI:10.1088/1361-6501/acf23c
摘要

Abstract Low-power electromagnetic-acoustic transducer (EMAT) is crucially important for safety-critical equipment in industry, especially for potential explosives and inflammable petrochemical equipment and facilities. When the excitation power is very low, the corresponding echoes are overwhelmed in noise and related measurement would be inaccurate. To solve this problem, this paper presents a new echo reconstruction method based on a deep stacked denoising autoencoder (DSDAE) for nondestructive evaluation. First, the uses of reference signals and new data structure are to improve the training efficiency. A hybrid method based on variational mode decomposition and wavelet transform is used to obtain clean reference signals as inputs of the deep network. Then, the modified network structure and loss function aim to improve the ability of feature extraction and reconstruct clean echoes from low-power EMAT signals. To validate the effectiveness of the proposed method, the experiments of self-excitation and receiving A-scan inspections of stepped specimens with different thicknesses are conducted at some excitation voltages, as low as 25 V. The results indicate that the proposed DSDAE shows better and more stable denoising performance than some popular processing methods for different specimens and excitation voltages. It greatly improves the signal-to-noise ratio of the reconstructed signal to 20 dB. When applying to thickness measurement of specimens, its relative error is lower than 0.3%, which provides a practical and accurate tool for low-power EMAT testing.

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
刚刚
无花果应助时纤采纳,获得20
3秒前
3秒前
cangmingzi发布了新的文献求助10
3秒前
3秒前
wangmengcheng完成签到,获得积分10
5秒前
自然冬卉完成签到 ,获得积分20
8秒前
fj完成签到,获得积分10
8秒前
善学以致用应助大鹅采纳,获得10
9秒前
KevinT应助水工佬采纳,获得30
9秒前
9秒前
kern发布了新的文献求助10
10秒前
CipherSage应助王乐康采纳,获得10
10秒前
单纯凝丹发布了新的文献求助10
10秒前
归尘完成签到,获得积分10
13秒前
Aliya完成签到 ,获得积分10
14秒前
16秒前
16秒前
求助应助julysuunh采纳,获得10
18秒前
NexusExplorer应助玩命的靖仇采纳,获得10
19秒前
19秒前
科研通AI6.1应助hhhh采纳,获得10
20秒前
xu发布了新的文献求助10
20秒前
21秒前
22秒前
Ecarc发布了新的文献求助10
22秒前
充电宝应助好吧采纳,获得10
23秒前
单纯凝丹完成签到,获得积分10
24秒前
立麦发布了新的文献求助10
24秒前
小马甲应助木木采纳,获得10
24秒前
如风过境完成签到 ,获得积分10
25秒前
26秒前
读书完成签到,获得积分10
27秒前
关耳完成签到,获得积分10
27秒前
科研通AI2S应助曾经的寇采纳,获得10
28秒前
mo给mo的求助进行了留言
28秒前
jinxli完成签到 ,获得积分10
28秒前
28秒前
28秒前
yoooooooo完成签到,获得积分20
28秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
Modern Epidemiology, Fourth Edition 5000
Digital Twins of Advanced Materials Processing 2000
Weaponeering, Fourth Edition – Two Volume SET 2000
Polymorphism and polytypism in crystals 1000
Signals, Systems, and Signal Processing 610
Discrete-Time Signals and Systems 610
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 纳米技术 有机化学 物理 生物化学 化学工程 计算机科学 复合材料 内科学 催化作用 光电子学 物理化学 电极 冶金 遗传学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 6024936
求助须知:如何正确求助?哪些是违规求助? 7659153
关于积分的说明 16177882
捐赠科研通 5173213
什么是DOI,文献DOI怎么找? 2768111
邀请新用户注册赠送积分活动 1751427
关于科研通互助平台的介绍 1637618